Name: Chenghao Liu
Type: User
Company: Beijing Institute of Technology
Bio: PhD candidate | Deep learning for medical image analysis | LLM | Computer graphics | C, C++, Python, CUDA
Location: Beijing, China
Chenghao Liu's Projects
A super light-weight CPU deep learning framework with no external dependency.
a simple CMake template
[WIP] Implementation of DDPM from scratch.
DeepWMH: Annotation-free white matter hyperintensity (WMH) lesion segmentation tool using deep learning.
Fully-connected (dense) 3D CRF for processing biomedical scans
A global illumination framework for rendering photorealistic images.
simple baseline JPEG image IO utility
My personal introduction.
Nifticlib is a C I/O library for reading and writing files in the nifti-1 data format. nifti-1 is a binary file format for storing medical image data, e.g. magnetic resonance image (MRI) and functional MRI (fMRI) brain images.
A simple utility to visualize 3D NIFTI image based on Python3.
A simple anomaly detection algorithm for medical imaging based on multi-atlas image registration and negative log likelihood.
《Machine Learning Systems: Design and Implementation》- Chinese Version
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (『飞桨』核心框架,深度学习&机器学习高性能单机、分布式训练和跨平台部署)
👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.
Procedural mesh and texture generator with local rendering support
Tiny software rasterizer with programmable shader & skeletal animation support written in C++.
Unsupervised Learning for Image Registration
voxr: a very light-weight, simple but effective NVIDIA GPU voxel renderer used for visualizing 3D voxels, such as visualizing 3D biomedical images. Implemented with CUDA C++ and NVRTC.